© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71040
    Prev
    Next
    INDEX
    Explanations

    geometric attributes, measures, and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     machining
    0.50
     adrenal
    0.47
    ق
    0.47
     maquin
    0.46
     workmanship
    0.46
     kidney
    0.45
     dha
    0.45
     jakim
    0.45
     conhe
    0.43
     lockdown
    0.43
    POSITIVE LOGITS
     সংলাপ
    0.45
    Tareas
    0.44
    obut
    0.43
    Checkbox
    0.43
    '],
    0.43
    dialog
    0.42
    länd
    0.42
    gradient
    0.41
    రాలు
    0.41
    opening
    0.41
    Activations Density 0.008%

    No Known Activations